activePromoteSoftwareActionPayload
TODO
activePromoteResultActionPayload
TODO
inputGraphPath
TODO
inputActionPayloadRootPath
TODO
outputGraphPath
TODO
mergeAndGetStrategy
TODO
sparkDriverMemory
memory for driver process
sparkExecutorMemory
memory for individual executor
sparkExecutorCores
number of cores used by single executor
oozieActionShareLibForSpark2
oozie action sharelib for spark 2.*
spark2ExtraListeners
com.cloudera.spark.lineage.NavigatorAppListener
spark 2.* extra listeners classname
spark2SqlQueryExecutionListeners
com.cloudera.spark.lineage.NavigatorQueryListener
spark 2.* sql query execution listeners classname
spark2YarnHistoryServerAddress
spark 2.* yarn history server address
spark2EventLogDir
spark 2.* event log dir location
${jobTracker}
${nameNode}
oozie.action.sharelib.for.spark
${oozieActionShareLibForSpark2}
Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]
${(activePromoteSoftwareActionPayload eq "true") and
(fs:exists(concat(concat(concat(concat(wf:conf('nameNode'),'/'),wf:conf('inputGraphPath')),'/'),'software')) eq "true") and
(fs:exists(concat(concat(concat(concat(wf:conf('nameNode'),'/'),wf:conf('inputActionPayloadRootPath')),'/'),'clazz=eu.dnetlib.dhp.schema.oaf.Software')) eq "true")}
yarn-cluster
cluster
PromoteSoftwareActionPayloadForSoftwareTable
eu.dnetlib.dhp.actionmanager.promote.PromoteActionPayloadForGraphTableJob
dhp-actionmanager-${projectVersion}.jar
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--inputGraphTablePath${inputGraphPath}/software
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Software
--inputActionPayloadPath${inputActionPayloadRootPath}/clazz=eu.dnetlib.dhp.schema.oaf.Software
--actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Software
--outputGraphTablePath${workingDir}/software
--mergeAndGetStrategy${mergeAndGetStrategy}
-pb
${inputGraphPath}/software
${workingDir}/software
${(activePromoteResultActionPayload eq "true") and
(fs:exists(concat(concat(concat(concat(wf:conf('nameNode'),'/'),wf:conf('inputActionPayloadRootPath')),'/'),'clazz=eu.dnetlib.dhp.schema.oaf.Result')) eq "true")}
yarn-cluster
cluster
PromoteResultActionPayloadForSoftwareTable
eu.dnetlib.dhp.actionmanager.promote.PromoteActionPayloadForGraphTableJob
dhp-actionmanager-${projectVersion}.jar
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=2560
--inputGraphTablePath${workingDir}/software
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Software
--inputActionPayloadPath${inputActionPayloadRootPath}/clazz=eu.dnetlib.dhp.schema.oaf.Result
--actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Result
--outputGraphTablePath${outputGraphPath}/software
--mergeAndGetStrategy${mergeAndGetStrategy}
-pb
${workingDir}/software
${outputGraphPath}/software